Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 19109
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "ison" with different contexts and possibly associated ideas

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of "ison" or "isolation"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    undo
    -0.87
    appers
    -0.84
    astically
    -0.81
    estones
    -0.78
    astical
    -0.77
    uled
    -0.74
    ulative
    -0.73
    atics
    -0.70
    izoph
    -0.70
    aiden
    -0.69
    POSITIVE LOGITS
    naire
    0.84
    ette
    0.83
    eers
    0.82
    nette
    0.82
    xual
    0.79
    eering
    0.78
    nect
    0.78
    ements
    0.78
    ese
    0.77
    ous
    0.77
    Activations Density 0.032%

    No Known Activations